//**********************************************************************************************************************
vector<string> FilterSeqsCommand::setParameters(){
try {
- CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta);
- CommandParameter phard("hard", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(phard);
- CommandParameter ptrump("trump", "String", "", "*", "", "", "",false,false); parameters.push_back(ptrump);
- CommandParameter psoft("soft", "Number", "", "0", "", "", "",false,false); parameters.push_back(psoft);
- CommandParameter pvertical("vertical", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pvertical);
- CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors);
- CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir);
- CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir);
+ CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","fasta-filter",false,true, true); parameters.push_back(pfasta);
+ CommandParameter phard("hard", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(phard);
+ CommandParameter ptrump("trump", "String", "", "*", "", "", "","",false,false, true); parameters.push_back(ptrump);
+ CommandParameter psoft("soft", "Number", "", "0", "", "", "","",false,false); parameters.push_back(psoft);
+ CommandParameter pvertical("vertical", "Boolean", "", "T", "", "", "","",false,false, true); parameters.push_back(pvertical);
+ CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false, true); parameters.push_back(pprocessors);
+ CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
+ CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
vector<string> myArray;
for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
}
}
//**********************************************************************************************************************
+string FilterSeqsCommand::getOutputPattern(string type) {
+ try {
+ string pattern = "";
+
+ if (type == "fasta") { pattern = "[filename],filter.fasta"; }
+ else if (type == "filter") { pattern = "[filename],filter"; }
+ else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
+
+ return pattern;
+ }
+ catch(exception& e) {
+ m->errorOut(e, "FilterSeqsCommand", "getOutputPattern");
+ exit(1);
+ }
+}
+//**********************************************************************************************************************
FilterSeqsCommand::FilterSeqsCommand(){
try {
abort = true; calledHelp = true;
fasta = validParameter.validFile(parameters, "fasta", false);
if (fasta == "not found") {
fasta = m->getFastaFile();
- if (fasta != "") { fastafileNames.push_back(fasta); m->mothurOut("Using " + fasta + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
+ if (fasta != "") {
+ fastafileNames.push_back(fasta);
+ m->mothurOut("Using " + fasta + " as input file for the fasta parameter."); m->mothurOutEndLine();
+ string simpleName = m->getSimpleName(fasta);
+ filterFileName += simpleName.substr(0, simpleName.find_first_of('.'));
+ }
else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
}
else {
ofstream outFilter;
//prevent giantic file name
- string filterFile;
- if (fastafileNames.size() > 3) { filterFile = outputDir + "merge.filter"; }
- else { filterFile = outputDir + filterFileName + ".filter"; }
+ map<string, string> variables;
+ variables["[filename]"] = outputDir + filterFileName + ".";
+ if (fastafileNames.size() > 3) { variables["[filename]"] = outputDir + "merge."; }
+ string filterFile = getOutputFileName("filter", variables);
m->openOutputFile(filterFile, outFilter);
outFilter << filter << endl;
for (int i = 0; i < lines.size(); i++) { delete lines[i]; } lines.clear();
- string filteredFasta = outputDir + m->getRootName(m->getSimpleName(fastafileNames[s])) + "filter.fasta";
+ map<string, string> variables;
+ variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastafileNames[s]));
+ string filteredFasta = getOutputFileName("fasta", variables);
#ifdef USE_MPI
int pid, numSeqsPerProcessor, num;
int tag = 2001;
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case
#else
- vector<unsigned long long> positions = savedPositions[s];
- #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+
+ vector<unsigned long long> positions;
+ if (savedPositions.size() != 0) { positions = savedPositions[s]; }
+ else {
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
+ positions = m->divideFile(fastafileNames[s], processors);
+#else
+ if(processors != 1){
+ int numFastaSeqs = 0;
+ positions = m->setFilePosFasta(fastafileNames[s], numFastaSeqs);
+ if (positions.size() < processors) { processors = positions.size(); }
+ }
+#endif
+ }
+ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
//vector<unsigned long long> positions = m->divideFile(fastafileNames[s], processors);
for (int i = 0; i < (positions.size()-1); i++) {
}
- if((i+1) % 100 == 0){ cout << (i+1) << endl; m->mothurOutJustToLog(toString(i+1) + "\n"); }
+ if((i+1) % 100 == 0){ cout << (i+1) << endl; }
}
if(outputString != ""){ //output to file
delete buf;
}
- if((num) % 100 != 0){ cout << (num) << endl; m->mothurOutJustToLog(toString(num) + "\n"); }
+ if((num) % 100 != 0){ cout << (num) << endl; }
return 0;
}
count++;
}
- #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
unsigned long long pos = in.tellg();
if ((pos == -1) || (pos >= filePos->end)) { break; }
#else
#endif
//report progress
- if((count) % 100 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
+ if((count) % 100 == 0){ m->mothurOutJustToScreen(toString(count)+"\n"); }
}
//report progress
- if((count) % 100 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
+ if((count) % 100 != 0){ m->mothurOutJustToScreen(toString(count)+"\n"); }
out.close();
int num = 0;
processIDS.clear();
-#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
//loop through and create all the processes you want
//Close all thread handles and free memory allocations.
for(int i=0; i < pDataArray.size(); i++){
num += pDataArray[i]->count;
+ if (pDataArray[i]->count != pDataArray[i]->end) {
+ m->mothurOut("[ERROR]: process " + toString(i) + " only processed " + toString(pDataArray[i]->count) + " of " + toString(pDataArray[i]->end) + " sequences assigned to it, quitting. \n"); m->control_pressed = true;
+ }
CloseHandle(hThreadArray[i]);
delete pDataArray[i];
}
#else
vector<unsigned long long> positions;
- #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
positions = m->divideFile(fastafileNames[s], processors);
for (int i = 0; i < (positions.size()-1); i++) {
lines.push_back(new linePair(positions[i], positions[(i+1)]));
}else {
int numFastaSeqs = 0;
positions = m->setFilePosFasta(fastafileNames[s], numFastaSeqs);
+ if (positions.size() < processors) { processors = positions.size(); }
//figure out how many sequences you have to process
int numSeqsPerProcessor = numFastaSeqs / processors;
count++;
}
- #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+ #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
unsigned long long pos = in.tellg();
if ((pos == -1) || (pos >= filePos->end)) { break; }
#else
#endif
//report progress
- if((count) % 100 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
+ if((count) % 100 == 0){ m->mothurOutJustToScreen(toString(count)+"\n"); }
}
//report progress
- if((count) % 100 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); }
+ if((count) % 100 != 0){ m->mothurOutJustToScreen(toString(count)+"\n"); }
in.close();
return count;
cout.flush();
//report progress
- if((i+1) % 100 == 0){ cout << (i+1) << endl; m->mothurOutJustToLog(toString(i+1) + "\n"); }
+ if((i+1) % 100 == 0){ cout << (i+1) << endl; }
}
//report progress
- if((num) % 100 != 0){ cout << num << endl; m->mothurOutJustToLog(toString(num) + "\n"); }
+ if((num) % 100 != 0){ cout << num << endl; }
return 0;
}
int num = 0;
processIDS.clear();
-#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux)
+#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
//loop through and create all the processes you want
while (process != processors) {
//Close all thread handles and free memory allocations.
for(int i=0; i < pDataArray.size(); i++){
num += pDataArray[i]->count;
+ if (pDataArray[i]->count != pDataArray[i]->end) {
+ m->mothurOut("[ERROR]: process " + toString(i) + " only processed " + toString(pDataArray[i]->count) + " of " + toString(pDataArray[i]->end) + " sequences assigned to it, quitting. \n"); m->control_pressed = true;
+ }
F.mergeFilter(pDataArray[i]->F.getFilter());
for (int k = 0; k < alignmentLength; k++) { F.a[k] += pDataArray[i]->F.a[k]; }